wrapping up for Ola

.idea/.gitignore

@@ -0,0 +1,8 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml

.idea/inspectionProfiles/Project_Default.xml

@@ -0,0 +1,30 @@
+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="PyPackageRequirementsInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ignoredPackages">
+        <value>
+          <list size="1">
+            <item index="0" class="java.lang.String" itemvalue="pytest-runner" />
+          </list>
+        </value>
+      </option>
+    </inspection_tool>
+    <inspection_tool class="PyPep8NamingInspection" enabled="true" level="WEAK WARNING" enabled_by_default="true">
+      <option name="ignoredErrors">
+        <list>
+          <option value="N801" />
+          <option value="N806" />
+        </list>
+      </option>
+    </inspection_tool>
+    <inspection_tool class="PyUnresolvedReferencesInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ignoredIdentifiers">
+        <list>
+          <option value="dict.labels" />
+          <option value="geograpy.places.countries" />
+        </list>
+      </option>
+    </inspection_tool>
+  </profile>
+</component>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.10 (hackathon)" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/review-claim.iml" filepath="$PROJECT_DIR$/.idea/review-claim.iml" />
+    </modules>
+  </component>
+</project>

.idea/review-claim.iml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="jdk" jdkName="Python 3.10 (hackathon)" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+  </component>
+</project>

.python-version

@@ -0,0 +1 @@
+hackathon

app.py

@@ -0,0 +1,72 @@
+import gradio as gr
+from huggingface_hub import get_repo_discussions, get_discussion_details
+from Crypto.PublicKey import RSA
+from Crypto.Cipher import AES, PKCS1_OAEP
+import base64
+
+
+def decrypt_claim(encrypted_claim_encoded, private_key_file):
+    base64_encoded = encrypted_claim_encoded.split("\n")[1]
+    encrypted_claim_encoded = encrypted_claim_encoded.split('\n')[1]
+    b64_fixed = bytes(base64_encoded[2:-1], 'utf-8')
+    encrypted_claim = base64.b64decode(b64_fixed)
+
+    private_key = RSA.import_key(open(private_key_file.name).read())
+
+    enc_session_key, nonce, tag, ciphertext = \
+        [encrypted_claim for x in (private_key.size_in_bytes(), 16, 16, -1)]
+
+    # Decrypt the session key with the private RSA key
+    cipher_rsa = PKCS1_OAEP.new(private_key)
+    session_key = cipher_rsa.decrypt(enc_session_key)
+
+    # Decrypt the data with the AES session key
+    cipher_aes = AES.new(session_key, AES.MODE_EAX, nonce)
+    data = cipher_aes.decrypt_and_verify(ciphertext, tag)
+    decrypted_claim = data.decode("utf-8")
+
+    return decrypted_claim
+
+
+def get_claim(claim_id, private_key):
+    claims = []
+
+    # TODO: Currently fetching ALL discussions, in case we want to build a view to see list of discussions in the claim-review space
+    # for discussion in get_repo_discussions(repo_id="Team8/dataset", repo_type="dataset"):
+    #     claims = claims + [discussion]
+    #     # print(f"{discussion.num} - {discussion.title}, pr: {discussion.is_pull_request}")
+    #
+    # claim = [c for c in claims if c.num == claim_id][0]
+
+    claim = get_discussion_details(
+        repo_id="Team8/dataset",
+        repo_type="dataset",
+        discussion_num=int(claim_id)
+    )
+
+    return gr.Textbox.update(value=claim.title), gr.Textbox.update(value=decrypt_claim(claim.events[0].content, private_key))
+
+
+demo = gr.Blocks()
+
+with demo:
+    gr.Markdown(
+        """
+    # Flip Text!
+    Start typing below to see the output.
+    """
+    )
+    button = gr.Button(value="Fetch Claim")
+    private_key = gr.File(label="Private Key")
+
+    claim_id = gr.Number()
+    claim_title = gr.Textbox(label="Claim Title", value="")
+    claim_text = gr.Textbox(label="Claim Text", value="")
+
+    button.click(
+        fn=get_claim,
+        inputs=[claim_id, private_key],
+        outputs=[claim_title, claim_text]
+    )
+
+demo.launch()

decrypt.py

@@ -0,0 +1,18 @@
+from Crypto.PublicKey import RSA
+from Crypto.Cipher import AES, PKCS1_OAEP
+
+file_in = open("encrypted_data.bin", "rb")
+
+private_key = RSA.import_key(open("private.pem").read())
+
+enc_session_key, nonce, tag, ciphertext = \
+   [ file_in.read(x) for x in (private_key.size_in_bytes(), 16, 16, -1) ]
+
+# Decrypt the session key with the private RSA key
+cipher_rsa = PKCS1_OAEP.new(private_key)
+session_key = cipher_rsa.decrypt(enc_session_key)
+
+# Decrypt the data with the AES session key
+cipher_aes = AES.new(session_key, AES.MODE_EAX, nonce)
+data = cipher_aes.decrypt_and_verify(ciphertext, tag)
+print(data.decode("utf-8"))

encrypt.py

@@ -0,0 +1,25 @@
+from Crypto.PublicKey import RSA
+from Crypto.Random import get_random_bytes
+from Crypto.Cipher import AES, PKCS1_OAEP
+
+from huggingface_hub import hf_hub_download
+
+import yaml
+import io
+
+loc = hf_hub_download(repo_id="Team8/dataset", repo_type="dataset", filename="receiver.pem")
+data = "I met aliens in UFO. Here is the map.".encode("utf-8")
+file_out = open("encrypted_data.bin", "wb")
+
+recipient_key = RSA.import_key(open(loc).read())
+session_key = get_random_bytes(16)
+
+# Encrypt the session key with the public RSA key
+cipher_rsa = PKCS1_OAEP.new(recipient_key)
+enc_session_key = cipher_rsa.encrypt(session_key)
+
+# Encrypt the data with the AES session key
+cipher_aes = AES.new(session_key, AES.MODE_EAX)
+ciphertext, tag = cipher_aes.encrypt_and_digest(data)
+[ file_out.write(x) for x in (enc_session_key, cipher_aes.nonce, tag, ciphertext) ]
+file_out.close()

encrypted_data.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3982bcc86b1f5ffdfc8ed12d9cef4fce794d92aad44e661a5dad9f474f0e4ddd
+size 325

gen_keys.py

@@ -0,0 +1,12 @@
+from Crypto.PublicKey import RSA
+
+key = RSA.generate(2048)
+private_key = key.export_key()
+file_out = open("private.pem", "wb")
+file_out.write(private_key)
+file_out.close()
+
+public_key = key.publickey().export_key()
+file_out = open("receiver.pem", "wb")
+file_out.write(public_key)
+file_out.close()

mykey.pem

@@ -0,0 +1,27 @@
+-----BEGIN RSA PRIVATE KEY-----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+-----END RSA PRIVATE KEY-----

private.pem

@@ -0,0 +1,27 @@
+-----BEGIN RSA PRIVATE KEY-----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+-----END RSA PRIVATE KEY-----

public_key.pem

@@ -0,0 +1,9 @@
+-----BEGIN PUBLIC KEY-----
+MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEA2nXsl3K5c2IhY23sSOdv
+fxSxjG/CqiWBqpljyk9pv/eRGgJrFGQMRiG/09Rkf4185PbUC66/nOeOHPgaSzrk
+ReOpFpfm7Gp0t4PeM5CZKx9V5TUwx0w3usZUgytU1ikKj6kVlJ+ZiBEUM3lrL7Mg
+0uzobXwZ/psoOFhqDbeCCEjHI1HXz4DwGhXKV5DE2fFAYFRdkdwlGDuhd3Q45ZHz
+G96awBkpgGTiFNwJN2dp2mV7T6cSL8fApSIqWDUZVSm7JYfYVBQcCbyRtwROfF5/
+dwlh95W6jQ7BHgytHDBvet5H/CaMAsm4ANbvjjbryMSdHSk2M2BbJdaUBqCo4Aym
+IwIDAQAB
+-----END PUBLIC KEY-----

receiver.pem

@@ -0,0 +1,9 @@
+-----BEGIN PUBLIC KEY-----
+MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEAnOjzZicSMFoD8sVcHq5F
+k9HeryaMdlC8ZivIpo0NCd+85rtlWN/LA0h7AQoQJbN/Ri8l2ZfqXmfGKINgpjUs
+FIgVvMOOIT1fiXXANQvNsTaWbJY0uDO4Z1WbWXjIZ6SbZ7FuID4hsHPpG0+uwUcx
+/L3rPya2JRYbOKag5UED5sRHKAdNc9aInzZzOmomyaaA6Btnj9lSX+w65ps/Gi5o
+a18j9aBda/On8WxTNcfBPjxqkyCvqW82te2+XGB8xUllllw2luqERLro9PrkLXV8
+ZhXWqiF909HCw+U6z9MhIoFAmuROEy/pS7Pl9T2h/UUac9SoeNA3EN1qxXpmg/b8
+PwIDAQAB
+-----END PUBLIC KEY-----

requirements.txt

@@ -0,0 +1,5 @@
+gradio
+huggingface_hub
+pycryptodome
+datasets
+pyyaml

scratch.py

@@ -0,0 +1,48 @@
+from huggingface_hub import get_repo_discussions, get_discussion_details
+
+# from huggingface_hub import DatasetFilter, HfApi
+from huggingface_hub import hf_hub_download
+#
+# claim = get_discussion_details(
+#     repo_id="Team8/dataset",
+#     repo_type="dataset",
+#     discussion_num=int(1)
+# )
+#
+# print(claim.events[0].content)
+
+from Crypto.PublicKey import RSA
+key = RSA.generate(2048)
+pub = key.public_key()
+
+f = open('mykey.pem','wb')
+f.write(key.export_key('PEM'))
+f.close()
+
+f = open('public_key.pem','wb')
+f.write(pub.export_key('PEM'))
+f.close()
+
+
+# api = HfApi()
+# filt = DatasetFilter(
+#     author="Team8",
+#     dataset_name="dataset"
+# )
+#
+# dsets = api.list_datasets(filter=filt)[0]
+
+# print(dsets)
+
+from huggingface_hub import hf_hub_download
+
+loc = hf_hub_download(repo_id="Team8/dataset", repo_type="dataset", filename="README.md")
+
+import yaml
+
+with open(loc) as f:
+    front_matter = next(yaml.load_all(f, Loader=yaml.FullLoader))
+    print(front_matter["public_key"])
+
+
+RSA

test.py

@@ -0,0 +1,29 @@
+from Crypto.PublicKey import RSA
+from Crypto.Cipher import AES, PKCS1_OAEP
+from huggingface_hub import get_repo_discussions, get_discussion_details
+import base64
+
+claim = get_discussion_details(
+    repo_id="Team8/dataset",
+    repo_type="dataset",
+    discussion_num=int(5)
+)
+
+encryptedtext_encoded = claim.events[0].content
+encrypted_text = base64.b64decode(encryptedtext_encoded)
+
+file_in = open("encrypted_data.bin", "rb")
+
+private_key = RSA.import_key(open("private.pem").read())
+
+enc_session_key, nonce, tag, ciphertext = \
+   [ file_in.read(x) for x in (private_key.size_in_bytes(), 16, 16, -1) ]
+
+# Decrypt the session key with the private RSA key
+cipher_rsa = PKCS1_OAEP.new(private_key)
+session_key = cipher_rsa.decrypt(enc_session_key)
+
+# Decrypt the data with the AES session key
+cipher_aes = AES.new(session_key, AES.MODE_EAX, nonce)
+data = cipher_aes.decrypt_and_verify(ciphertext, tag)
+print(data.decode("utf-8"))